Research Papers

The security of printed circuit boards (PCBs) has become increasingly vital as supply chain vulnerabilities, including tampering, present significant risks to electronic systems. While detecting tampering on a PCB is the first step for verification, forensics is also needed to identify the modified component. One non-invasive and reliable PCB tamper detection technique with global coverage is the impedance characterization of a PCB's power delivery network (PDN). However, it is an open question whether one can use the two-dimensional impedance signatures for forensics purposes. In this work, we introduce a novel PCB forensics approach using explainable AI (XAI) on impedance signatures. Through extensive experiments, we replicate various PCB tamper events, generating a dataset used to develop an XAI algorithm capable of not only detecting tampering but also explaining why the algorithm makes a decision about whether a tamper event has happened. At the core of our XAI algorithm is a random forest classifier with an accuracy of 96.7%, sufficient to explain the algorithm's decisions. To understand the behavior of the classifier in the decision-making process, we utilized SHAP values as an XAI tool to determine which frequency component influences the classifier's decision for a particular class the most. This approach enhances detection capabilities as well as advancing the verifier's ability to reverse-engineer and analyze two-dimensional impedance signatures for forensics.

We introduce a novel learning and planning framework that replaces traditional reward-based optimisation with constructive logical inference. In our model, actions, transitions, and goals are represented as logical propositions, and decision-making proceeds by building constructive proofs under intuitionistic logic. This method ensures that state transitions and policies are accepted only when supported by verifiable preconditions -- eschewing probabilistic trial-and-error in favour of guaranteed logical validity. We implement a symbolic agent operating in a structured gridworld, where reaching a goal requires satisfying a chain of intermediate subgoals (e.g., collecting keys to open doors), each governed by logical constraints. Unlike conventional reinforcement learning agents, which require extensive exploration and suffer from unsafe or invalid transitions, our constructive agent builds a provably correct plan through goal chaining, condition tracking, and knowledge accumulation. Empirical comparison with Q-learning demonstrates that our method achieves perfect safety, interpretable behaviour, and efficient convergence with no invalid actions, highlighting its potential for safe planning, symbolic cognition, and trustworthy AI. This work presents a new direction for reinforcement learning grounded not in numeric optimisation, but in constructive logic and proof theory.

We introduce an interpretable deep learning framework that predicts the cohesive energy of transition-metal alloys (TMAs) by embedding cohesion theory within graph neural networks (GNNs). Beyond accurate prediction of cohesive energy, a key indicator of thermodynamic stability, the model offers mechanistic insights by disentangling energy contributions into physically meaningful components. These data-driven interpretations reveal periodic trends and stability principles governing transition metals. We apply the model to single-atom alloys (SAAs) to assess their thermodynamic resilience against two destabilizing processes: agglomeration (adatom clustering) and segregation (migration into the subsurface). Our analysis shows that these phenomena are governed by distinct physical factors-agglomeration is primarily influenced by localized d-orbital coupling, while segregation is dictated by delocalized effects such as wavefunction renormalization. This model thus serves as an explainable AI tool for understanding and guiding the design of stable TMAs, with implications for catalysis and materials discovery.

Composable Building Blocks for Controllable and Transparent Interactive AI Systems

Sebe Vanbrabant, Gustavo Rovelo Ruiz, Davy Vanacken

While the increased integration of AI technologies into interactive systems enables them to solve an equally increasing number of tasks, the black box problem of AI models continues to spread throughout the interactive system as a whole. Explainable AI (XAI) techniques can make AI models more accessible by employing post-hoc methods or transitioning to inherently interpretable models. While this makes individual AI models clearer, the overarching system architecture remains opaque. To this end, we propose an approach to represent interactive systems as sequences of structural building blocks, such as AI models and control mechanisms grounded in the literature. These can then be explained through accompanying visual building blocks, such as XAI techniques. The flow and APIs of the structural building blocks form an explicit overview of the system. This serves as a communication basis for both humans and automated agents like LLMs, aligning human and machine interpretability of AI models. We discuss a selection of building blocks and concretize our flow-based approach in an architecture and accompanying prototype interactive system.

As large language models (LLMs) become more powerful and pervasive across society, ensuring these systems are beneficial, safe, and aligned with human values is crucial. Current alignment techniques, like Constitutional AI (CAI), involve complex iterative processes. This paper argues that the Method of Wide Reflective Equilibrium (MWRE) -- a well-established coherentist moral methodology -- offers a uniquely apt framework for understanding current LLM alignment efforts. Moreover, this methodology can substantively augment these processes by providing concrete pathways for improving their dynamic revisability, procedural legitimacy, and overall ethical grounding. Together, these enhancements can help produce more robust and ethically defensible outcomes. MWRE, emphasizing the achievement of coherence between our considered moral judgments, guiding moral principles, and relevant background theories, arguably better represents the intricate reality of LLM alignment and offers a more robust path to justification than prevailing foundationalist models or simplistic input-output evaluations. While current methods like CAI bear a structural resemblance to MWRE, they often lack its crucial emphasis on dynamic, bi-directional revision of principles and the procedural legitimacy derived from such a process. While acknowledging various disanalogies (e.g., consciousness, genuine understanding in LLMs), the paper demonstrates that MWRE serves as a valuable heuristic for critically analyzing current alignment efforts and for guiding the future development of more ethically sound and justifiably aligned AI systems.

As AI systems are increasingly tested and deployed in open-ended and high-stakes domains, crowdworkers are often tasked with responsible AI (RAI) content work. These tasks include labeling violent content, moderating disturbing text, or simulating harmful behavior for red teaming exercises to shape AI system behaviors. While prior research efforts have highlighted the risks to worker well-being associated with RAI content work, far less attention has been paid to how these risks are communicated to workers by task designers or individuals who design and post RAI tasks. Existing transparency frameworks and guidelines, such as model cards, datasheets, and crowdworksheets, focus on documenting model information and dataset collection processes, but they overlook an important aspect of disclosing well-being risks to workers. In the absence of standard workflows or clear guidance, the consistent application of content warnings, consent flows, or other forms of well-being risk disclosure remains unclear. This study investigates how task designers approach risk disclosure in crowdsourced RAI tasks. Drawing on interviews with 23 task designers across academic and industry sectors, we examine how well-being risk is recognized, interpreted, and communicated in practice. Our findings highlight the need to support task designers in identifying and communicating risks not only to support crowdworker well-being but also to strengthen the ethical integrity and technical efficacy of AI development pipelines.

The delivery of high-quality, low-latency video streams is critical for remote autonomous vehicle control, where operators must intervene in real time. However, reliable video delivery over Fourth/Fifth-Generation (4G/5G) mobile networks is challenging due to signal variability, mobility-induced handovers, and transient congestion. In this paper, we present a comprehensive blueprint for an integrated video quality monitoring system, tailored to remote autonomous vehicle operation. Our proposed system includes subsystems for data collection onboard the vehicle, video capture and compression, data transmission to edge servers, real-time streaming data management, Artificial Intelligence (AI) model deployment and inference execution, and proactive decision-making based on predicted video quality. The AI models are trained on a hybrid dataset that combines field-trial measurements with synthetic stress segments and covers Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and encoder-only Transformer architectures. As a proof of concept, we benchmark 20 variants from these model classes together with feed-forward Deep Neural Network (DNN) and linear-regression baselines, reporting accuracy and inference latency. Finally, we study the trade-offs between onboard and edge-based inference. We further discuss the use of explainable AI techniques to enhance transparency and accountability during critical remote-control interventions. Our proactive approach to network adaptation and Quality of Experience (QoE) monitoring aims to enhance remote vehicle operation over next-generation wireless networks.

This paper calls on the research community not only to investigate how human biases are inherited by large language models (LLMs) but also to explore how these biases in LLMs can be leveraged to make society's "unwritten code" - such as implicit stereotypes and heuristics - visible and accessible for critique. We introduce a conceptual framework through a case study in science: uncovering hidden rules in peer review - the factors that reviewers care about but rarely state explicitly due to normative scientific expectations. The idea of the framework is to push LLMs to speak out their heuristics through generating self-consistent hypotheses - why one paper appeared stronger in reviewer scoring - among paired papers submitted to 46 academic conferences, while iteratively searching deeper hypotheses from remaining pairs where existing hypotheses cannot explain. We observed that LLMs' normative priors about the internal characteristics of good science extracted from their self-talk, e.g., theoretical rigor, were systematically updated toward posteriors that emphasize storytelling about external connections, such as how the work is positioned and connected within and across literatures. Human reviewers tend to explicitly reward aspects that moderately align with LLMs' normative priors (correlation = 0.49) but avoid articulating contextualization and storytelling posteriors in their review comments (correlation = -0.14), despite giving implicit reward to them with positive scores. These patterns are robust across different models and out-of-sample judgments. We discuss the broad applicability of our proposed framework, leveraging LLMs as diagnostic tools to amplify and surface the tacit codes underlying human society, enabling public discussion of revealed values and more precisely targeted responsible AI.

Poor interpretability hinders the practical applicability of multi-agent reinforcement learning (MARL) policies. Deploying interpretable surrogates of uninterpretable policies enhances the safety and verifiability of MARL for real-world applications. However, if these surrogates are to interact directly with the environment within human supervisory frameworks, they must be both performant and computationally efficient. Prior work on interpretable MARL has either sacrificed performance for computational efficiency or computational efficiency for performance. To address this issue, we propose HYDRAVIPER, a decision tree-based interpretable MARL algorithm. HYDRAVIPER coordinates training between agents based on expected team performance, and adaptively allocates budgets for environment interaction to improve computational efficiency. Experiments on standard benchmark environments for multi-agent coordination and traffic signal control show that HYDRAVIPER matches the performance of state-of-the-art methods using a fraction of the runtime, and that it maintains a Pareto frontier of performance for different interaction budgets.

AI-driven automation generates broad-based social benefit only if technical gains become visible, durable, and publicly claimable. We develop a policy-facing stress test by extending a standard task-automation growth model with an AI capability parameter that raises productivity on automatable tasks while holding the set of tasks fixed. The exercise is intentionally limited: it is not a forecast of AI timelines or a full welfare analysis, but a way to identify which institutions determine whether AI rents can support broad transfers. Calibrated to U.S. quantities, the model shows that capability alone is not decisive. Public capture, deployment costs, automation scope, and market structure jointly determine when AI gains become shareable. The main policy lesson is that moving from low to moderate public capture (33\%) can substitute for substantial AI capability growth, while pushing capture further to full nationalization yields smaller gains, especially if deployment or safety costs are high. Competition policy also has distributional consequences: opening concentrated AI markets may improve fairness and resilience, but can reduce the rent pool unless alternative public-claim institutions are built. Cross-nationally, tax-heavy systems lower the needed AI capability threshold through stronger effective revenue collection, while Singaporean and Abu Dhabi-style public-asset models show that governments can also capture AI gains through ownership and investment returns rather than taxes alone. Our framework therefore identifies which levers governments can act on now to make future AI gains easier to measure, claim, and distribute broadly.

Contemporary discussions in AI ethics often treat culture as a source of normative divergence that needs to be accommodated, tolerated, or managed due to its resistance to universal standards. This paper offers an alternative vision through the concept of "Cultural Co-Genesis of AI Ethics." Rather than viewing culture as a boundary or container of isolated moral systems, we argue that it is a generative space for ethical co-production. In this framework, ethical values emerge through intercultural engagement, dialogical encounters, mutual recognition, and shared moral inquiry. This approach resists both universalist imposition and relativistic fragmentation. Cultures are not approached as absolutes to be defended or dissolved, but as co-authors of a dynamic ethical landscape. By grounding AI ethics in Cultural Co-Genesis, we move from managing difference to constructing shared ethical meaning for AI ethics, with culture as a partner, not a problem. We support this framework with two cases: (1) a theoretical analysis of how various cultures interpret the emergence of powerful new species, challenging dominant existential risk narratives, and (2) an empirical study of global AI ethics principles using data from the Linking AI Principles project, which reveals deep ethical convergence despite cultural diversity. We conclude that cross-cultural AI ethics should be seen not as an ethical patchwork, but as a mosaic in progress, woven from the normative insights that emerge between cultures.

The EU AI Act makes explainability urgent for high-risk AI systems, yet most XAI research focuses on technical metrics rather than regulatory compliance. Understanding how legal requirements reshape XAI method design is challenging: the AI Act regulates organizational relationships (providers, deployers) using legal terminology, specifies obligations without concrete technical requirements, and underrepresents end-users--the very stakeholders whose needs human-centered XAI addresses. As regulations emerge globally, human-centered XAI practitioners face both a challenge and an opportunity: regulations pull XAI research toward real-world deployment, while practitioners can actively shape how explainability enables compliance. This establishes a bidirectional relationship. Our contribution is threefold. First, we provide the first interdisciplinary analysis of XAI's role in the AI Act--conducted by a team comprising AI Act legal experts, ML engineers, and requirements engineers--on a real-world clinical decision support system. Second, we systematically align XAI stakeholder roles with AI Act legal responsibilities, revealing where explainability methods address regulatory requirements versus where additional measures are necessary. Third, we identify three key opportunities for human-centered XAI practitioners: actively defining their roles in regulatory implementation; making the user-to-affected-party relationship explicit where regulations address only provider-deployer obligations; and enabling compliance while building multi-level trust--from regulators to affected parties.